CN116434065B - Water body segmentation method for panchromatic geometric correction remote sensing image - Google Patents
Water body segmentation method for panchromatic geometric correction remote sensing image Download PDFInfo
- Publication number
- CN116434065B CN116434065B CN202310423497.7A CN202310423497A CN116434065B CN 116434065 B CN116434065 B CN 116434065B CN 202310423497 A CN202310423497 A CN 202310423497A CN 116434065 B CN116434065 B CN 116434065B
- Authority
- CN
- China
- Prior art keywords
- remote sensing
- sensing image
- water body
- full
- region
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 title claims abstract description 123
- 238000000034 method Methods 0.000 title claims abstract description 34
- 230000011218 segmentation Effects 0.000 title claims abstract description 22
- 238000012937 correction Methods 0.000 title claims abstract description 21
- 210000000746 body region Anatomy 0.000 claims abstract description 20
- 238000005260 corrosion Methods 0.000 claims abstract description 12
- 230000007797 corrosion Effects 0.000 claims abstract description 12
- 238000007781 pre-processing Methods 0.000 claims abstract description 7
- 238000000605 extraction Methods 0.000 claims description 7
- 238000001914 filtration Methods 0.000 claims description 6
- 238000012545 processing Methods 0.000 abstract description 6
- 238000013135 deep learning Methods 0.000 description 4
- 238000010606 normalization Methods 0.000 description 3
- 238000011161 development Methods 0.000 description 2
- 230000018109 developmental process Effects 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000003628 erosive effect Effects 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 238000009499 grossing Methods 0.000 description 1
- 238000007726 management method Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012549 training Methods 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
- 238000003809 water extraction Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/10—Terrestrial scenes
- G06V20/182—Network patterns, e.g. roads or rivers
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/20—Image enhancement or restoration using local operators
- G06T5/30—Erosion or dilatation, e.g. thinning
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/13—Edge detection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
- G06V10/26—Segmentation of patterns in the image field; Cutting or merging of image elements to establish the pattern region, e.g. clustering-based techniques; Detection of occlusion
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10032—Satellite or aerial image; Remote sensing
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20021—Dividing image into blocks, subimages or windows
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30181—Earth observation
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02A—TECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE
- Y02A90/00—Technologies having an indirect contribution to adaptation to climate change
- Y02A90/30—Assessment of water resources
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Multimedia (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Image Analysis (AREA)
- Image Processing (AREA)
Abstract
The invention relates to a water body segmentation method of a full-color geometric correction remote sensing image, which comprises the following steps: acquiring an original full-color remote sensing image containing land and a water area and preprocessing the original full-color remote sensing image; determining reserved pixel points according to brightness and gradient of the preprocessed full-color remote sensing image; performing image corrosion on the full-color remote sensing image processed by the pixel points according to the resolution; utilizing a seed point region growing algorithm to grow a water body region; and removing the non-water body area. By implementing the scheme, the water body region can be extracted from the panchromatic geometric correction remote sensing image rapidly and efficiently through the processing of the brightness value, the gradient value and the overall shape of the water body target region of the panchromatic geometric correction remote sensing image, and the method does not depend on high-performance computing resources.
Description
Technical Field
The invention relates to the technical field of remote sensing image processing, in particular to a water body segmentation method for full-color geometric correction remote sensing images.
Background
The water body is an important resource for human society, and the rapid and accurate acquisition of the position information of the water body has great significance for the aspects of national resource management, planning development, rapid disaster assessment and the like. The development of water extraction of remote sensing images has been carried out for decades, from the initial manual visual judgment method, to semi-automatic auxiliary judgment by utilizing spatial information and texture information, to the current most-hot high-precision water identification based on deep learning, and new technology is layered endlessly.
Aiming at the full-color geometric correction remote sensing image water segmentation, the water region can be extracted more accurately by deep learning, but the deep learning method needs to collect a large number of samples and accurately mark the water segmentation samples, so that the cost is high, the period is long, and meanwhile, a great amount of computing resources are consumed in the training process of the deep learning method, so that the efficiency is low. Only the traditional method is improved, and the water body segmentation of the full-color remote sensing image can be realized rapidly and efficiently.
Disclosure of Invention
In order to solve the technical problems in the prior art, the invention aims to provide a water body segmentation method for full-color geometric correction remote sensing images, which can rapidly and efficiently extract water body areas from the full-color geometric correction remote sensing images without depending on high-performance computing resources.
In order to achieve the above purpose, the technical scheme of the invention is as follows:
the embodiment of the invention provides a water body segmentation method of a full-color geometric correction remote sensing image, which comprises the following steps:
acquiring an original full-color remote sensing image containing land and a water area and preprocessing the original full-color remote sensing image;
determining reserved pixel points according to brightness and gradient of the preprocessed full-color remote sensing image;
performing image corrosion on the full-color remote sensing image processed by the pixel points according to the resolution;
utilizing a seed point region growing algorithm to grow a water body region;
and removing the non-water body area.
According to one aspect of an embodiment of the present invention, the preprocessing includes:
geometrically correcting the original full-color remote sensing image;
counting the pixel value of each pixel point in the geometrically corrected panchromatic remote sensing image, and normalizing the pixel value to obtain a corresponding brightness value;
and removing the black edge area with the brightness value of 0.
According to one aspect of the embodiment of the present invention, the storage format of the original full-color remote sensing image is a 16-bit unsigned short type.
According to an aspect of the embodiment of the present invention, the determining the reserved pixel point according to the brightness and the gradient of the preprocessed panchromatic remote sensing image includes:
counting the brightness value and the gradient value of each pixel point in the preprocessed panchromatic remote sensing image;
determining a brightness threshold according to the overall darkness characteristic of a water body region in the full-color remote sensing image, and reserving pixel points corresponding to brightness values lower than the brightness threshold;
and determining a gradient threshold according to the characteristic of smoothing the water body region in the full-color remote sensing image, and reserving pixel points corresponding to gradient values lower than the gradient threshold.
According to one aspect of the embodiment of the invention, the gradient value is calculated based on a Sobel operator, and the specific process is that 3x3 Sobel space filtering is respectively carried out on each pixel in the horizontal direction and the vertical direction, then the filtering values in the horizontal direction and the vertical direction are used for obtaining the gradient amplitude value according to the following formula,
wherein G is x And G y Representing the filtered values in the horizontal and vertical directions, respectively.
According to one aspect of the embodiment of the present invention, the brightness threshold is set as a pixel value normalization of the pixel pointsObtaining the maximum brightness value after the processingThe gradient threshold value is set as the maximum gradient amplitude value calculated based on Sobel operator
According to an aspect of the embodiment of the present invention, the image erosion of the full-color remote sensing image after pixel processing according to the resolution includes:
calculating the resolution of the panchromatic remote sensing image and the size of the water body region to obtain convolution kernels with matched sizes;
dividing the full-color remote sensing image processed by the pixel points into binary images, wherein the foreground of the binary images is white representing possible water body pixels, and the background is black representing non-water body pixels;
and performing corrosion operation by using the full-color remote sensing image processed by the convolution check pixel points, removing discrete white prospects with smaller areas, and reserving continuous targets with larger areas.
According to one aspect of the embodiment of the present invention, the water body region growing by using the seed point region growing algorithm includes:
carrying out contour extraction on the corroded full-color remote sensing image in a water body area;
randomly extracting white pixel points in each independent disjoint contour coverage area to serve as seed points;
setting a pixel gray level difference value to perform seed point region growth in the original full-color remote sensing image by taking eight connectivity as a criterion, wherein the region growth threshold is twice the mean square error of the brightness value of the corroded foreground region, and continuously growing according to the eight connectivity region of the 3*3 window until all pixels which have connectivity and meet the requirement of the region growth threshold are traversed.
According to one aspect of the embodiment of the present invention, the removing the non-water area includes:
extracting the outline of a water body area obtained by the growth of the seed point area;
and calculating the area and the length and the width of each extracted partial water body region, removing the region which does not meet the conditions, and obtaining the water body segmentation result by using the remaining contour surrounding region.
According to an aspect of the embodiment of the present invention, the rejection condition is: the calculated area of the water body area is lower than an area threshold value of the water body distributed in the image, and the calculated length and width of the water body area are lower than a length and width threshold value of the water body distributed in the image.
Compared with the prior art, the invention has the following beneficial effects:
according to the embodiment of the invention, the brightness value and the gradient value of the full-color geometric correction remote sensing image are utilized to perform image preliminary processing, the seed point is obtained, the water body area is obtained through the growth of the seed point area, and finally the water body area is calculated through contour extraction, so that the non-conforming water body area is removed. The method realizes the rapid and accurate extraction of the water body region in the full-color remote sensing image data, does not require high-performance computing resources, and has great significance for the rapid extraction of the water body region in the full-color remote sensing image data.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings that are required to be used in the embodiments will be briefly described below. It is apparent that the drawings in the following description are only some embodiments of the present invention, and that other drawings may be obtained from these drawings without inventive effort for a person of ordinary skill in the art.
FIG. 1 schematically illustrates a flow chart of a method for segmenting a body of water from a full-color geometrically corrected remote sensing image in accordance with an embodiment of the present invention;
FIG. 2 schematically shows the results of water body segmentation disclosed in an embodiment of the present invention.
Detailed Description
The description of the embodiments of this specification should be taken in conjunction with the accompanying drawings, which are a complete description of the embodiments. In the drawings, the shape or thickness of the embodiments may be enlarged and indicated simply or conveniently. Furthermore, portions of the structures in the drawings will be described in terms of separate descriptions, and it should be noted that elements not shown or described in the drawings are in a form known to those of ordinary skill in the art.
Any references to directions and orientations in the description of the embodiments herein are for convenience only and should not be construed as limiting the scope of the invention in any way. The following description of the preferred embodiments will refer to combinations of features, which may be present alone or in combination, and the invention is not particularly limited to the preferred embodiments. The scope of the invention is defined by the claims.
As shown in fig. 1, the embodiment discloses a water body segmentation method for full-color geometric correction remote sensing images, which specifically includes the following steps:
s110, acquiring an original full-color remote sensing image containing land and water area and preprocessing.
In this embodiment, the preprocessing in step S110 includes: performing geometric correction on an original full-color remote sensing image containing land and water areas, counting the pixel value of each pixel point in the full-color remote sensing image after geometric correction, and normalizing the pixel values to obtain corresponding brightness values.
Further, the original panchromatic remote sensing image is stored in a 16-bit unsigned short type. Firstly, the maximum value and the minimum value of all pixels in the full-color remote sensing image after geometric correction are counted during normalization, all pixel values are normalized according to the following formula,
wherein P is R For the original pixel value, P N For normalized pixel values, i.e. luminance values, min_p and max_p are the minimum and maximum values, respectively, of the original pixel values.
And removing the black edge region with the brightness value of 0 according to the characteristic that the black edge only exists at the image edge. Because the full-color remote sensing image needs to be subjected to rotation operation during geometric correction, pixels with brightness value of 0 appear in the edge area of the image, and the pixels are ineffective in water segmentation and can interfere with water segmentation, so that the pixels need to be removed in advance. Because of the minimum value of the unsigned type when 0, the normalized pixel value is also 0, and according to the characteristic, the black edge of the full-color image after geometric correction can be removed, so that the accuracy and the efficiency of the subsequent water body recognition result are improved.
And S120, determining reserved pixel points according to the brightness and gradient of the preprocessed full-color remote sensing image.
In this embodiment, the specific process of determining the reserved pixel point in step S120 according to the brightness and gradient of the preprocessed full-color remote sensing image includes: counting the brightness value and the gradient value of each pixel point in the preprocessed panchromatic remote sensing image; determining a proper brightness threshold according to the characteristic of overall darkness of a water body region in the full-color remote sensing image, and reserving pixel points corresponding to the brightness values lower than the brightness threshold; and determining a proper gradient threshold according to the characteristic of smoother water body areas in the full-color remote sensing image, and reserving pixel points corresponding to gradient values lower than the gradient threshold.
Further, the luminance value is obtained based on the normalization in step S110 described above. The gradient value is calculated based on a Sobel operator, the specific process is that 3x3 Sobel space filtering is respectively carried out on each pixel in the horizontal direction and the vertical direction, then the filtering values in the horizontal direction and the vertical direction are used for obtaining the gradient amplitude value according to the following formula,
wherein G is x And G y The filtering values in the horizontal direction and the vertical direction are respectively indicated, and in particular,
preferably, go upThe brightness threshold value is set to be the maximum brightness value 255Namely 64; according to the water statistics of a large amount of full-color remote sensing image data, except for the increase of the brightness of the water caused by very special flare, the brightness of the water in the full-color remote sensing image is basically smaller than 64. The set brightness threshold is used to preserve the water pixels as much as possible, but at the same time preserve some dark targets on land, such as dense vegetation, shadows of buildings, etc. The gradient threshold is set to be +.f. of the maximum gradient magnitude value calculated based on Sobel operator>Because the water body is smooth, the gradient amplitude value is smaller, and the gradient amplitude value of the absolute (large) part of water body pixels does not exceed the maximum amplitude value except a small amount of water body pixels near the bank>Therefore, the gradient threshold value can be utilized to remove pixels such as dense vegetation, building shadows and the like.
And S130, performing image corrosion on the full-color remote sensing image processed by the pixel points according to the resolution. The core area of the water body target can be obtained through image corrosion, and the joint of the water body and the land area can be accurately identified.
In this embodiment, the specific process of performing image corrosion on the full-color remote sensing image processed by the pixel point according to the resolution in step S130 includes:
and calculating the resolution of the panchromatic remote sensing image and the size of the water body region to obtain a convolution kernel with matched size. Because the typical water body area on the remote sensing image can reach a certain area, length and width, otherwise, the area of the default water body of the embodiment is at least 25m 2 The length and width are at least 5 meters. The corresponding pixel value can be calculated according to the area and the length and the width, if the spatial resolution of the remote sensing image is 1 meter, thenThe area of the body of water is 25 pixels, and the length and width are 5 pixels. The corrosion operation is to ensure that the water body with the minimum area and length and width is not completely corroded, so that the water body can be set to be 3x3.
Dividing the full-color remote sensing image processed by the pixel points into binary images, wherein the foreground of the binary images is white representing possible water body pixels, and the background is black representing non-water body pixels;
and performing corrosion operation by using the full-color remote sensing image processed by the convolution check pixel points, removing discrete white prospects with smaller areas, and reserving continuous targets with larger areas. According to the characteristics of water distribution, the probability that the foreground with larger area is water is larger, and the discrete targets are dark targets which cannot be removed by brightness and gradient.
And S140, performing water body region growth by using a seed point region growth algorithm.
In this embodiment, the specific process of performing the water body region growth by using the seed point region growth algorithm in step S140 includes:
and extracting the outline of the water body region from the corroded full-color remote sensing image. The corroded area of the binarized image can be determined as a water body target, the contour of the water body target is extracted, the binarized image can be converted into a water body area with a target level, and each individual target can be processed later.
White pixels are randomly extracted as seed points within each individual disjoint outline coverage area. The purpose of the seed points is to perform region growing in the normalized image to obtain a uniformly distributed water body.
Setting a pixel gray difference value to perform seed point region growth in the original full-color remote sensing image by taking eight connectivity as a criterion, wherein the region growth threshold is twice the mean square error of the brightness value of the corroded foreground region, and continuously growing according to the eight connectivity region of the 3*3 window until all pixels which have connectivity and meet the requirement of the region growth threshold are traversed.
In this embodiment, the purpose of the seed point region growing is to obtain a continuously distributed water region as much as possible, but some non-water objects may be scattered, and because the brightness and gradient amplitude values of these non-water objects are smaller and are mistakenly identified as water, and the corrosion operation cannot be completely removed, some non-water regions may still exist after the region growing. Therefore, the following step S150 is required to be performed to remove the non-water area.
In this embodiment, the specific process of removing the non-water area in step S150 includes: and extracting the outline of the water body area obtained by the growth of the seed point area. The areas and the length and the width of the coverage areas of the water contours of the parts are extracted through calculation, the areas which do not meet the conditions are removed, the remaining contour coverage areas are obtained water segmentation results, as shown in fig. 2, the images from left to right in fig. 2 are the original geometrically corrected full-color remote sensing images and the final obtained water segmentation images in sequence, in the water segmentation images, the white areas are segmented water areas, and the black areas are land areas. Because the water body is distributed in the image with a certain area and length and width, the areas which do not meet the requirements after the contour extraction can be removed according to the minimum area and length and width threshold values, and the residual contour surrounding areas are the final water body segmentation results. The specific rejection conditions are as follows: the calculated area of the water body area is lower than an area threshold value of the water body distributed in the image, and the calculated length and width of the water body area are lower than a length and width threshold value of the water body distributed in the image.
The water body segmentation method of the panchromatic geometric correction remote sensing image can be applied to the water body segmentation task of the panchromatic geometric correction remote sensing image through the steps. Firstly, carrying out image preliminary processing by utilizing brightness values and gradient values of the panchromatic geometric correction remote sensing image, obtaining seed points, obtaining a water body area through seed point area growth, and finally calculating the water body area through contour extraction so as to remove the non-conforming water body area, so that the water body area of the panchromatic remote sensing image can be extracted rapidly, efficiently and accurately, and high-performance computing resources are not required. The embodiment of the invention provides a method for the rapid detection task of the water body for the full-color remote sensing image, and has great practical application value and significance.
The sequence numbers of the steps related to the method of the present invention do not mean the sequence of the execution sequence of the method, and the execution sequence of the steps should be determined by the functions and the internal logic, and should not limit the implementation process of the embodiment of the present invention in any way.
The foregoing description of the preferred embodiments of the invention is not intended to be limiting, but rather to enable any modification, equivalent replacement, improvement or the like to be made within the spirit and principles of the invention.
Claims (8)
1. A water body segmentation method of a full-color geometric correction remote sensing image comprises the following steps:
acquiring an original full-color remote sensing image containing land and a water area and preprocessing the original full-color remote sensing image;
determining reserved pixel points according to brightness and gradient of the preprocessed full-color remote sensing image; the determining the reserved pixel point according to the brightness and the gradient of the preprocessed full-color remote sensing image comprises the following steps: counting the brightness value and the gradient value of each pixel point in the preprocessed panchromatic remote sensing image; determining a brightness threshold according to the overall darkness characteristic of a water body region in the full-color remote sensing image, and reserving pixel points corresponding to brightness values lower than the brightness threshold; determining a gradient threshold according to the characteristic of water body region smoothness in the full-color remote sensing image, and reserving pixel points corresponding to gradient values lower than the gradient threshold;
performing image corrosion on the full-color remote sensing image processed by the pixel points according to the resolution; the image corrosion of the full-color remote sensing image processed by the pixel points according to the resolution ratio comprises the following steps: calculating the resolution of the panchromatic remote sensing image and the size of the water body region to obtain convolution kernels with matched sizes; dividing the full-color remote sensing image processed by the pixel points into binary images, wherein the foreground of the binary images is white representing possible water body pixels, and the background is black representing non-water body pixels; performing corrosion operation by using the full-color remote sensing image processed by the convolution check pixel points, removing discrete white prospects with smaller areas, and reserving continuous foreground targets with larger areas;
utilizing a seed point region growing algorithm to grow a water body region;
and removing the non-water body area.
2. The method of claim 1, wherein the preprocessing comprises:
geometrically correcting the original full-color remote sensing image;
counting the pixel value of each pixel point in the geometrically corrected panchromatic remote sensing image, and normalizing the pixel value to obtain a corresponding brightness value;
and removing the black edge area with the brightness value of 0.
3. The method according to claim 1 or 2, wherein the original full-color remote sensing image is stored in a 16-bit unsigned short type.
4. The method of claim 1, wherein the gradient values are calculated based on a Sobel operator by performing Sobel spatial filtering of 3x3 for each pixel in a horizontal direction and a vertical direction, respectively, and obtaining gradient magnitude values according to the following formula using the filtered values in the horizontal direction and the vertical direction,
wherein G is x And G y Representing the filtered values in the horizontal and vertical directions, respectively.
5. The method according to claim 4, wherein the brightness threshold is set to a maximum brightness value obtained by normalizing the pixel values of the pixelsThe gradient threshold is set to be +.f. of the maximum gradient magnitude value calculated based on Sobel operator>
6. The method of claim 1, wherein the performing the water region growing using a seed point region growing algorithm comprises:
carrying out contour extraction on the corroded full-color remote sensing image in a water body area;
randomly extracting white pixel points in each independent disjoint contour coverage area to serve as seed points;
setting a pixel gray level difference value to perform seed point region growth in the original full-color remote sensing image by taking eight connectivity as a criterion, wherein the region growth threshold is twice the mean square error of the brightness value of the corroded foreground region, and continuously growing according to the eight connectivity region of the 3*3 window until all pixels which have connectivity and meet the requirement of the region growth threshold are traversed.
7. The method of claim 1, wherein the culling non-water regions comprises:
extracting the outline of a water body area obtained by the growth of the seed point area;
and calculating the area and the length and the width of each extracted partial water body region, removing the region which does not meet the conditions, and obtaining the water body segmentation result by using the remaining contour surrounding region.
8. The method of claim 7, wherein the culling conditions are: the calculated area of the water body area is lower than an area threshold value of the water body distributed in the image, and the calculated length and width of the water body area are lower than a length and width threshold value of the water body distributed in the image.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310423497.7A CN116434065B (en) | 2023-04-19 | 2023-04-19 | Water body segmentation method for panchromatic geometric correction remote sensing image |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310423497.7A CN116434065B (en) | 2023-04-19 | 2023-04-19 | Water body segmentation method for panchromatic geometric correction remote sensing image |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN116434065A CN116434065A (en) | 2023-07-14 |
| CN116434065B true CN116434065B (en) | 2023-12-19 |
Family
ID=87094146
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310423497.7A Active CN116434065B (en) | 2023-04-19 | 2023-04-19 | Water body segmentation method for panchromatic geometric correction remote sensing image |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116434065B (en) |
Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101901343A (en) * | 2010-07-20 | 2010-12-01 | 同济大学 | Remote sensing image road extracting method based on stereo constraint |
| CN101944233A (en) * | 2010-09-25 | 2011-01-12 | 西北工业大学 | Method for quickly extracting airport target in high-resolution remote sensing image |
| CN102298698A (en) * | 2011-05-30 | 2011-12-28 | 河海大学 | Remote sensing image airplane detection method based on fusion of angle points and edge information |
| CN108564056A (en) * | 2018-04-25 | 2018-09-21 | 中国水利水电科学研究院 | A kind of method of remote sensing image identifying water boy extraction |
| CN108960143A (en) * | 2018-07-04 | 2018-12-07 | 北京航空航天大学 | Detect deep learning method in a kind of naval vessel in High Resolution Visible Light remote sensing images |
| CN109800736A (en) * | 2019-02-01 | 2019-05-24 | 东北大学 | A kind of method for extracting roads based on remote sensing image and deep learning |
| CN110956101A (en) * | 2019-11-19 | 2020-04-03 | 广东省城乡规划设计研究院 | Remote sensing image yellow river ice detection method based on random forest algorithm |
| CN112052777A (en) * | 2020-09-01 | 2020-12-08 | 国交空间信息技术（北京）有限公司 | Cross-water bridge extraction method and device based on high-resolution remote sensing image |
| CN114092832A (en) * | 2022-01-20 | 2022-02-25 | 武汉大学 | High-resolution remote sensing image classification method based on parallel hybrid convolutional network |
| WO2022052032A1 (en) * | 2020-09-11 | 2022-03-17 | 京东方科技集团股份有限公司 | Image segmentation method and device, and three-dimensional reconstruction method and device for image |
| CN114757925A (en) * | 2022-04-22 | 2022-07-15 | 国网陕西省电力有限公司电力科学研究院 | Non-contact type high-voltage circuit breaker defect detection method and system |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US11907819B2 (en) * | 2019-11-20 | 2024-02-20 | University Of Connecticut | Systems and methods to generate high resolution flood maps in near real time |
-
2023
- 2023-04-19 CN CN202310423497.7A patent/CN116434065B/en active Active
Patent Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101901343A (en) * | 2010-07-20 | 2010-12-01 | 同济大学 | Remote sensing image road extracting method based on stereo constraint |
| CN101944233A (en) * | 2010-09-25 | 2011-01-12 | 西北工业大学 | Method for quickly extracting airport target in high-resolution remote sensing image |
| CN102298698A (en) * | 2011-05-30 | 2011-12-28 | 河海大学 | Remote sensing image airplane detection method based on fusion of angle points and edge information |
| CN108564056A (en) * | 2018-04-25 | 2018-09-21 | 中国水利水电科学研究院 | A kind of method of remote sensing image identifying water boy extraction |
| CN108960143A (en) * | 2018-07-04 | 2018-12-07 | 北京航空航天大学 | Detect deep learning method in a kind of naval vessel in High Resolution Visible Light remote sensing images |
| CN109800736A (en) * | 2019-02-01 | 2019-05-24 | 东北大学 | A kind of method for extracting roads based on remote sensing image and deep learning |
| CN110956101A (en) * | 2019-11-19 | 2020-04-03 | 广东省城乡规划设计研究院 | Remote sensing image yellow river ice detection method based on random forest algorithm |
| CN112052777A (en) * | 2020-09-01 | 2020-12-08 | 国交空间信息技术（北京）有限公司 | Cross-water bridge extraction method and device based on high-resolution remote sensing image |
| WO2022052032A1 (en) * | 2020-09-11 | 2022-03-17 | 京东方科技集团股份有限公司 | Image segmentation method and device, and three-dimensional reconstruction method and device for image |
| CN114092832A (en) * | 2022-01-20 | 2022-02-25 | 武汉大学 | High-resolution remote sensing image classification method based on parallel hybrid convolutional network |
| CN114757925A (en) * | 2022-04-22 | 2022-07-15 | 国网陕西省电力有限公司电力科学研究院 | Non-contact type high-voltage circuit breaker defect detection method and system |
Also Published As
| Publication number | Publication date |
|---|---|
| CN116434065A (en) | 2023-07-14 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Zhang et al. | Object-oriented shadow detection and removal from urban high-resolution remote sensing images | |
| US11580647B1 (en) | Global and local binary pattern image crack segmentation method based on robot vision | |
| Brandtberg et al. | Automated delineation of individual tree crowns in high spatial resolution aerial images by multiple-scale analysis | |
| CN105046252B (en) | A kind of RMB prefix code recognition methods | |
| CN111027446B (en) | Coastline automatic extraction method of high-resolution image | |
| CN106157323B (en) | A kind of insulator division and extracting method of dynamic division threshold value and block search combination | |
| CN107564017B (en) | Method for detecting and segmenting urban high-resolution remote sensing image shadow | |
| CN110287898A (en) | A kind of optical satellite remote sensing image cloud detection method of optic | |
| CN116110053B (en) | Container surface information detection method based on image recognition | |
| CN110428425B (en) | Sea-land separation method of SAR image based on coastline vector data | |
| CN109978848A (en) | Method based on hard exudate in multiple light courcess color constancy model inspection eye fundus image | |
| CN111783773B (en) | Correction method for angle-inclined telegraph pole signboard | |
| CN112734729B (en) | Water gauge water level line image detection method and device suitable for night light supplement condition and storage medium | |
| CN110874825B (en) | Method for extracting binary image of water trace on surface of composite insulator | |
| CN103778627A (en) | Sea oil spill detection method based on SAR image | |
| CN109191436A (en) | The low-dose CT Lung neoplasm detection algorithm of view-based access control model conspicuousness spectrum residual error method | |
| CN112529853A (en) | Method and device for detecting damage of netting of underwater aquaculture net cage | |
| US20210065376A1 (en) | Region Merging Image Segmentation Algorithm Based on Boundary Extraction | |
| CN117765287A (en) | Image target extraction method combining LWR and density clustering | |
| CN116434065B (en) | Water body segmentation method for panchromatic geometric correction remote sensing image | |
| US20230386023A1 (en) | Method for detecting medical images, electronic device, and storage medium | |
| CN114445814B (en) | Character region extraction method and computer-readable storage medium | |
| CN112329674B (en) | Icing lake detection method and device based on multi-texture feature fusion | |
| CN114677428A (en) | Power transmission line icing thickness detection method based on unmanned aerial vehicle image processing | |
| Shuaishuai et al. | Research on License Plate Recognition Algorithm Based on OpenCV |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |